Abstract: Techniques for object highlighting in an ecommerce short-form video are disclosed. The object highlighting can be associated with a product within the video, defining a highlighted product. The object highlighting can be performed automatically utilizing computer-implemented techniques. A short-form video from a library of short-form videos is accessed. A plurality of objects from a catalog of products featured in the short-form video is recognized. At least one of the plurality of objects displayed by a host is identified. A first object from the plurality of objects is selected. The first object is highlighted, which causes it to be surrounded by a boundary overlay in the short-form video. A representation of the first object is dynamically inserted into an on-screen product card. An ecommerce purchase of the first object is enabled within the short-form video.

Abstract: Disclosed embodiments provide techniques for dynamic population of contextually relevant videos in an ecommerce environment. A library of short-form videos is accessed from a server, and one or more short-form videos within the library is associated with a product for sale. In cases where a user searches for a product for sale on a website, a short-form video request is received. One or more short-form videos are selected from the library based on the product associations. In some instances, the video selection is optimized based on metadata, a bid from an advertiser, or machine learning. A container unit is inserted into the website and is dynamically populated with the short-form videos. A microsite is generated, enabling an ecommerce purchase. The microsite can use a product card or display a virtual purchase cart while the video plays.

Abstract: Disclosed embodiments provide techniques for automated video processing. Short-form videos are analyzed and video segments are created from the short-form videos. A related short-form video can be used to create a new video segment, promoting a short-form video. The new video segment is populated on the website by a floating video player or banner ad providing a link to the related short-form video. Video segments can promote and/or demonstrate a product and/or service. The video segments show and describe various aspects of a product. The video segments are disseminated to one or more websites. The video segments can be shown as video thumbnails, banner advertisements, or rich media advertisements. The video segments can be disseminated based on context, and different segments can be provided to different websites. The different video segments can be disseminated based on demographic information, geographic region, and/or other criteria.

Abstract: Techniques for video manipulation based on machine learned video curating are disclosed. Web page content is loaded, where the content includes a frame for short-form videos. The content of the web page is analyzed for textual information. A short-form video server is accessed. Short-form videos are selected from the short-form video server, where the selecting includes automatically curating the short-form videos. Adaptive learning is used for the selecting, based on a user's web page behavior. The adaptive learning includes collecting the user's web page behavior before the selecting. Automatic curating includes selecting, by a neural network, a subset of short-form videos appropriate for the web page. The web page frame is populated with the short-form videos obtained from the video server. Representations of the short-form videos are displayed within the frame on the web page. The short-form videos are auto played within the frame.

Abstract: Disclosed embodiments provide techniques for search using generative model synthesized images. An image, or set of images, is generated based on a text query, and the generated image or images are used as input to an image-based search query. In some instances, this technique provides more comprehensive and effective search results. In cases where a user wishes to search for something for which no known image currently exists, disclosed embodiments can provide more effective results than a text-based query. Disclosed embodiments generate an input image based on the text query using generative model synthesized image techniques. The input image is used to perform an image-based search, and sorted results are returned. Disclosed embodiments are particularly useful when searching for visual art in the form of images and/or videos.

Abstract: Techniques for video manipulation using a product card within a short-form video environment are disclosed. Display is accomplished using a video stream interface that can be executed on an electronic device associated with a user. The video stream, such as a short-form video or livestream video, can include one or more products. The display shows product cards associated with the products within the video. The product cards originate from a repository, a third-party website, or some other source. The product information includes text, video, and/or audio content. The user is provided an option to purchase one or more of the products presented within the video by selecting the product card. The viewer selects product cards displayed in front of the video to learn more about the products and/or purchase the products.

Abstract: Techniques for manipulating video livestream background images are disclosed. A short-form video, such as a livestream video or livestream replay video, can be analyzed for context. Computer-implemented techniques may be used for performing entity detection, and can also detect a change in subject based on speech and/or actions of a host individual. The subject can include a particular product. The detecting a change in subject can include detecting a foreground object and identifying the foreground object as a product. The identification of the foreground object as a product can include performing optical character recognition on text imprinted on a foreground object. The identification of the foreground object as a product can include image recognition techniques. The identification of the foreground object as a product can include scanning of an optical code such as a barcode that is imprinted on the product.

Abstract: Techniques for video usage within a frame widget retail environment are disclosed. A library of short-form videos is accessed. A website is evaluated for products represented within an online retail environment. One or more products are identified from the webpage that was evaluated. At least one short-form video is chosen from the library to be included in the webpage. The choosing of the at least one video is based on the identified product. A frame widget is inserted into the webpage. The placement of the frame widget is determined by the evaluation of the webpage. The frame widget is populated with at least one video that was chosen along with other videos. The video that was chosen is rendered in the frame widget. The rendering is accomplished by a user action.

Abstract: Disclosed techniques include video performance rendering modification based on device rotation metric. A media stream is received from a server. The media stream is targeted for display on a handheld media stream playback device. An orientation of the handheld device is determined during playback of the media stream on the handheld device. A change in the orientation of the handheld device is detected. The change occurs during playback of the media stream. Based on the detecting the change of orientation, a rotation angle of the handheld device is calculated. Based on the rotation angle, the playback speed of the media stream on the handheld device is changed. The changing the playback speed changes direction of playback rendering based on the rotation angle of the handheld device. The changing direction provides forward playback by rotating the handheld device in a clockwise direction from an initial orientation.

Abstract: The system provides a method and apparatus for automatically constructing, controlling, curating, recording, displaying, and preserving a discussion between one, two or more users on a topic. The system is an automated debate moderator that provides muting, time limits, number of rounds, round duration countdown, order of speaking, and end time that can be accessed via any processing device, including smartphones, tablets, desktops, laptops, and the like. The topics can be self-generated or selected from a list of curated topics and the resulting recorded debate can be linked to on any social network or media viewing platform.

Abstract: Techniques for video manipulation based on an immersive video experience including rotation are disclosed. Parameters pertaining to a video are determined. Second parameters pertaining to a video display are determined. A minimum scale value is calculated to inscribe a rectangle within an oval based on a height and a width of the video. A height and a width of the video display define the rectangle. A gravity sensor input is preprocessed using a low-pass filter before using it to determine the minimum scale value. The video is preprocessed using a video inset and a viewport inset. The video can be trimmed, and the rectangle can be scaled. A rectangular portion of the video is rendered on the video display wherein the rectangular portion is on or inside the boundaries of the oval.

Abstract: Techniques for display based on inline frame-based video rendering within browser are disclosed. A plurality of short-form videos is obtained. Thumbnails of one or more short-form videos, from the plurality of short-form videos, are displayed. The displaying thumbnails occurs within a frame on a third-party webpage within a browser window. A user's selection of a video from the short-form videos is received. The video that was selected by a user is reduced. The reducing the video enables the video to be rendered in a portion of the browser window. The reducing the video to render the video in a portion of the browser window includes launching a reloaded version of the third-party webpage to render the video superimposed over the third-party webpage. The video that was reduced is rendered, along with a reloaded copy of the third-party webpage, in the browser window.

Abstract: Disclosed techniques include audio and visual stream rendering modification based on device rotation metric. One or more media streams are received from a server. The one or more media streams are targeted for display on a handheld media stream playback device. An orientation of the handheld device is determined during playback of at least one of the one or more media streams on the handheld device. A change in orientation of the handheld device is detected. The change occurs during playback of the at least one of the one or more media streams. Based on detecting the change in orientation, a rotation angle of the handheld device is calculated. Based on the rotation angle, the playback of at least one of the one or more media streams is changed on the handheld device.

Abstract: Technologies relating to system and method of real-time video overlaying or superimposing display from multiple mutually synchronous cameras. are disclosed. An example method of real-time video overlaying includes the steps of: synchronizing frame rates of a depth data, a face meta data, and a video data of a first camera video output captured by a first camera; determining a first depth between a user face and the first camera; using a cutoff depth to determine a user body contour; generating a binary mask of the user body contour based on the first depth and the cutoff depth; smoothing an edge of the binary mask; merging the binary mask with the first camera video output and generating a merged first camera video output; and overlaying the merged first camera video output onto a second camera video output.

Abstract: Technologies relating to system and method of real-time video overlaying or superimposing display from multiple mutually synchronous cameras are disclosed. An example method of real-time video overlaying includes the steps of: synchronizing frame rates of a depth data, a face meta data, and a video data of a first camera video output captured by a first camera; determining a first depth between a user face and the first camera; using a cutoff depth to determine a user body contour; generating a binary mask of the user body contour based on the first depth and the cutoff depth; smoothing an edge of the binary mask; merging the binary mask with the first camera video output and generating a merged first camera video output; and overlaying the merged first camera video output onto a second camera video output.

Abstract: The system provides a method and apparatus for automatically constructing, controlling, curating, recording, displaying, and preserving a discussion between one, two or more users on a topic. The system is an automated debate moderator that provides muting, time limits, number of rounds, round duration countdown, order of speaking, and end time that can be accessed via any processing device, including smartphones, tablets, desktops, laptops, and the like. The topics can be self-generated or selected from a list of curated topics and the resulting recorded debate can be linked to on any social network or media viewing platform.

Abstract: Technologies relating to system and method of real-time video overlaying or superimposing display from multiple mutually synchronous cameras are disclosed. An example method of real-time video overlaying includes the steps of: synchronizing frame rates of a depth data, a face meta data, and a video data of a first camera video output captured by a first camera; determining a first depth between a user face and the first camera; using a cutoff depth to determine a user body contour; generating a binary mask of the user body contour based on the first depth and the cutoff depth; smoothing an edge of the binary mask; merging the binary mask with the first camera video output and generating a merged first camera video output; and overlaying the merged first camera video output onto a second camera video output.